6 datasets found

Formats: JSON Tags: visual reasoning

Filter Results

  • MathVista

    MathVista is a benchmark for evaluating mathematical reasoning in visual contexts.

  • ChartCheck

    ChartCheck is a novel, large-scale dataset for explainable fact-checking against real-world charts, consisting of 1.7k charts and 10.5k human-written claims and explanations.

  • Synthetic Visual Reasoning Test (SVRT)

    The Synthetic Visual Reasoning Test (SVRT) dataset consists of 23 binary classification tasks, each defined by a particular configuration of relations. The tasks can be broadly...

  • CLEVR-Robot Environment

    A benchmark for evaluating task compositionality and long-horizon tasks through object manipulation, with language serving as the mechanism for goal specification.

  • GQA

    The GQA dataset is a visual question answering dataset that characterizes in compositional question answering and visual reasoning about real-world images.

  • NLVR2

    The dataset used in the paper is a set of sequential vision-and-language tasks, where each task consists of an image and a text input.
You can also access this registry using the API (see API Docs).